Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
51Accuracy (Pass@4)
22
May 25, 2026
65.49Exact Match (EM)
22
Feb 26, 2026
83.05Accuracy
22
Feb 26, 2026
90Accuracy
22
Feb 26, 2026
0.73Exact Match
22
Feb 26, 2026
51.75Strict EM Accuracy @5
21
Jul 2, 2026
67.86str-em Accuracy (@5)
21
Jul 2, 2026
75.97str-EM Accuracy (@5)
21
Jul 2, 2026
58.31EM Accuracy (@5)
21
Jul 2, 2026
21.48LLM-as-a-judge Accuracy (@5)
21
Jul 2, 2026
45.74F1 Score
21
Jun 9, 2026
0.839F1 Score
21
Jun 1, 2026
70.14Accuracy (ARC-C)
21
Jun 30, 2026
40.85VWR
21
May 12, 2026
53.7VWR
21
May 12, 2026
64.8Accuracy
21
Apr 29, 2026
68.08F1
21
May 8, 2026
73.2Average Accuracy
21
Apr 24, 2026
85.1Accuracy
21
May 13, 2026
4.54CR
21
Apr 15, 2026
84.2Score
21
Jun 4, 2026
59.33Accuracy
21
Mar 27, 2026
58.2Accuracy
21
Mar 27, 2026
80.34Accuracy
21
Mar 27, 2026
92.6Accuracy
21
Mar 27, 2026